Fairness (also known as equity interchangeably) in machine learning is important for societal wellbeing, but limited public datasets hinder its progress. Currently, no dedicated public medical datasets with imaging data for fairness learning are available, though minority groups suffer from more health issues. To address this gap, we introduce Harvard Glaucoma Fairness (Harvard-GF), a retinal nerve disease dataset including 3,300 subjects with both 2D and 3D imaging data and balanced racial groups for glaucoma detection. Glaucoma is the leading cause of irreversible blindness globally with Blacks having doubled glaucoma prevalence than other races. We also propose a fair identity normalization (FIN) approach to equalize the feature importance between different identity groups. Our FIN approach is compared with various state-of-the-art fairness learning methods with superior performance in the racial, gender, and ethnicity fairness tasks with 2D and 3D imaging data, demonstrating the utilities of our dataset Harvard-GF for fairness learning. To facilitate fairness comparisons between different models, we propose an equity-scaled performance measure, which can be flexibly used to compare all kinds of performance metrics in the context of fairness. The dataset and code are publicly accessible via https://ophai.hms.harvard.edu/harvard-gf3300/.

Background: Circumpapillary retinal nerve fiber layer thickness (cpRNFLT) as assessed by spectral domain optical coherence tomography (SD-OCT) is a new technique used for the detection and evaluation of glaucoma and other optic neuropathies. Before translating cpRNFLT into clinics, it is crucially important to investigate anthropometric, biochemical, and clinical parameters potentially affecting cpRNFLT in a large population-based dataset. Methods: The population-based LIFE-Adult Study randomly selected 10,000 participants from the population registry of Leipzig, Germany. All participants underwent standardized systemic assessment of various cardiometabolic risk markers and ocular imaging, including cpRNFLT measurement using SD-OCT (Spectralis, Heidelberg Engineering). After employing strict SD-OCT quality criteria, 8952 individuals were analyzed. Multivariable linear regression analyses were used to evaluate the independent associations of various cardiometabolic risk markers with sector-specific cpRNFLT. For significant markers, the relative strength of the observed associations was compared to each other to identify the most relevant factors influencing cpRNFLT. In all analyses, the false discovery rate method for multiple comparisons was applied. Results: In the entire cohort, female subjects had significantly thicker global and also sectoral cpRNFLT compared to male subjects (p < 0.05). Multivariable linear regression analyses revealed a significant and independent association between global and sectoral cpRNFLT with biomarkers of renal function and lipid profile. Thus, thinner cpRNFLT was associated with worse renal function as assessed by cystatin C and estimated glomerular filtration rate. Furthermore, an adverse lipid profile (i.e., low high-density lipoprotein (HDL) cholesterol, as well as high total, high non-HDL, high low-density lipoprotein cholesterol, and high apolipoprotein B) was independently and statistically significantly related to thicker cpRNFLT. In contrast, we do not observe a significant association between cpRNFLT and markers of inflammation, glucose homeostasis, liver function, blood pressure, or obesity in our sector-specific analysis and globally. Conclusions: Markers of renal function and lipid metabolism are predictors of sectoral cpRNFLT in a large and deeply phenotyped population-based study independently of previously established covariates. Future studies on cpRNFLT should include these biomarkers and need to investigate whether incorporation will improve the diagnosis of early eye diseases based on cpRNFLT.

Ophthalmic images, along with their derivatives like retinal nerve fiber layer (RNFL) thickness maps, play a crucial role in detecting and monitoring eye diseases such as glaucoma. For computer-aided diagnosis of eye diseases, the key technique is to automatically extract meaningful features from ophthalmic images that can reveal the biomarkers (e.g., RNFL thinning patterns) associated with functional vision loss. However, representation learning from ophthalmic images that links structural retinal damage with human vision loss is non-trivial mostly due to large anatomical variations between patients. This challenge is further amplified by the presence of image artifacts, commonly resulting from image acquisition and automated segmentation issues. In this paper, we present an artifact-tolerant unsupervised learning framework called EyeLearn for learning ophthalmic image representations in glaucoma cases. EyeLearn includes an artifact correction module to learn representations that optimally predict artifact-free images. In addition, EyeLearn adopts a clustering-guided contrastive learning strategy to explicitly capture the affinities within and between images. During training, images are dynamically organized into clusters to form contrastive samples, which encourage learning similar or dissimilar representations for images in the same or different clusters, respectively. To evaluate EyeLearn, we use the learned representations for visual field prediction and glaucoma detection with a real-world dataset of glaucoma patient ophthalmic images. Extensive experiments and comparisons with state-of-the-art methods confirm the effectiveness of EyeLearn in learning optimal feature representations from ophthalmic images.

Purpose: The purpose of this study was to assess the accuracy of artificial neural networks (ANN) in estimating the severity of mean deviation (MD) from peripapillary retinal nerve fiber layer (RNFL) thickness measurements derived from optical coherence tomography (OCT). Methods: Models were trained using 1796 pairs of visual field and OCT measurements from 1796 eyes to estimate visual field MD from RNFL data. Multivariable linear regression, random forest regressor, support vector regressor, and 1D convolutional neural network (CNN) models with sectoral RNFL thickness measurements were examined. Three independent subsets consisting of 698, 256, and 691 pairs of visual field and OCT measurements were used to validate the models. Estimation errors were visualized to assess model performance subjectively. Mean absolute error (MAE), root mean square error (RMSE), median absolute error, Pearson correlation, and R-squared metrics were used to assess model performance objectively. Results: The MAE and RMSE of the ANN model based on the testing dataset were 4.0 dB (95% confidence interval = 3.8–4.2) and 5.2 dB (95% confidence interval = 5.1–5.4), respectively. The ranges of MAE and RMSE of the ANN model on independent datasets were 3.3–5.9 dB and 4.4–8.4 dB, respectively. Conclusions: The proposed ANN model estimated MD from RNFL measurements better than multivariable linear regression model, random forest, support vector regressor, and 1-D CNN models. The model was generalizable to independent data from different centers and varying races. Translational Relevance: Successful development of ANN models may assist clinicians in assessing visual function in glaucoma based on objective OCT measures with less dependence on subjective visual field tests.